检索结果-内蒙古大学图书馆

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Adityan, Arjun Kabeleswar Vaiapury, Karthikeyan Palanisamy, T. Tangavel, Senthil Kumar Amrita Vishwa Vidyapeetham Department of Mathematics Coimbatore India Iitm Research Park Tcs Research and Innovation Chennai India Amrita School of Physical Sciences Department of Mathematics Amrita Vishwa Vidyapeetham Coimbatore India Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9798331523923

We provide a novel approach for altering existing fashion designs through the integration of text-guided diffusion models with perceptual loss optimization. Effective technology for design evolution and modification is crucial for the rapid design iteration and prototyping of the fashion industry. We propose a pipeline that combines a LoRA-fine-tuned Stable Diffusion model with a perceptual loss to guarantee structural and stylistic faithfulness. The initial part is training a dedicated text-to-image generation model using fashion-specific data, subsequently refining the outputs through a perceptual loss mechanism to maintain structural integrity and improve stylistic coherence. After training with the DeepFashion-MultiModal dataset and evaluating performance on a custom dataset of essential garments, our method demonstrates exceptional preservation of stylistic coherence and structural integrity. Our approach offers a viable alternative for the automated transformation of fashion design while enhancing creative workflows within the fashion sector. © 2025 IEEE.

关键词： Hosiery manufacture

来源：评论

学校读者我要写书评

暂无评论

Innovative Video Classification Method based on Deep Learning Approach

引用

Recent Patents on Engineering 2025年第2期19卷 95-107页

作者： Hemamalini, V. Jayasutha, D. Vinothini, V.R. Devi, R. Manjula Kumar, A. Anitha, E. Department of Networking and Communications School of Computing SRM Institute of Science and Technology Chennai India Department of Computer Science and Engineering Arjun College of Technology Coimbatore Thamaraikulam India Department of Mathematics Bannari Amman Institute of Technology Sathyamangalam Erode638401 India Department of Computer Science and Design Kongu Engineering College Perundurai Erode638060 India Department of Civil Engineering University Institute of Engineering & Technology Maharshi Dayanand University Rohtak124001 India Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore641202 India

Background: The automated classification of videos through artificial neural networks is addressed in this work. To explore the concepts and measure the results, the data set UCF101 is used, consisting of video clips taken from YouTube to recognize actions. The study is carried out with the authors' resources to determine the feasibility of independent research in the area. Methods: This work was developed in the Python programming language using the Keras library with Tensorflow as the back-end. The objective is to develop a network that presents performance compatible with the state of the art in terms of classifying videos according to the actions taken. Results: Given the hardware limitations, there is considerable distance between the implementation possibilities in this work and what is known as the state-of-the-art. Conclusion: Throughout the work, some aspects in which this limitation influenced the development are presented, but it is shown that this realization is feasible and that obtaining expressive results is possible 98.6% accuracy is obtained in the UCF101 data set, compared to the 98 percentage points of the best result ever reported, using, however, considerably fewer resources. In addition, the importance of transfer learning in achieving expressive results as well as the different performances of each architecture are reviewed. Thus, this work may open doors to carry patent-based outcomes. © 2025 Bentham science Publishers.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Decoherence implies information gain

引用

Physical Review Research 2025年第1期7卷 L012040-L012040页

作者： Dorje C. Brody Lane P. Hughston School of Mathematics and Physics University of Surrey Guildford GU2 7XH United Kingdom Institute of Industrial Science The University of Tokyo Tokyo 153-0041 Japan Department of Computing Goldsmiths University of London New Cross London SE14 6NW United Kingdom

It is shown that if the wave function of a quantum system undergoes an arbitrary random transformation such that the diagonal elements of the density matrix in the decoherence basis associated with a preferred observable remain constant, then (i) the off-diagonal elements of the density matrix become smaller in magnitude, and (ii) the state of the system gains information about the preferred observable from its environment in the sense that the uncertainty of the observable is reduced in the transformed state. These results do not depend on the details of how the system-environment interaction generates the random state transformation, and together imply that decoherence leads, in general, to information gain, not information loss.

关键词： Wave functions

来源：评论

学校读者我要写书评

暂无评论

Spectral Analysis and Stability of Wave Equations with Dispersive Nonlinearity

arXiv

引用

arXiv 2025年

作者： Dauda, Umar Muhammad Ja'afaru, Lawal Department of Mathematics Faculty of Computing & Mathematical Sciences Kano University of Science and Technology Kano Wudil Nigeria

This study employs spectral methods to capture the behaviour of wave equation with dispersive-nonlinearity. We describe the evolution of hump initial data and track the conservation of the mass and energy functionals. The dispersive-nonlinearity results to solution in an extended Schwartz space via analytic approach. We construct numerical schemes based on spectral methods to simulate soliton interactions under Schwartzian initial data. The computational analysis includes validation of energy and mass conservation to ensure numerical accuracy. Results show that initial data from the Schwartz space decompose into smaller wave-packets due to the weaker dispersive-nonlinearity but leads to wave collapse as a result of stronger dispersive-nonlinearity. We conjecture that the hyperbolic equation with a positive nonlinearity and exponent σ ≥ 2 admits global solutions, while lower exponents lead to localized solutions. A stability analysis of solitonic solutions of the equation is provided via the perturbation approach. © 2025, CC BY.

关键词： Solitons

来源：评论

学校读者我要写书评

暂无评论

Astronomical Image Clustering Using Spectral, K-Means and Mean Shift

Astronomical Image Clustering Using Spectral, K-Means and Me...

引用

computing for Sustainability and Intelligent Future (COMP-SIF), International Conference on

作者： Vaishnavi Shivaji Mohite Krishna Gayatri Patra CH Hari Sankar Sarada Jayan Department of Computer Science Amrita School of Computing Bengaluru Department of Mathematics Amrita School of Engineering Bengaluru

ISBN: (数字)9798331538538

ISBN: (纸本)9798331538545

By analyzing vast amounts of observational data through astronomical image analysis, you can gain valuable information about the structure of the universe. This paper presents a new method for clustering astronomical images that uses both spectral and K-means methods and also incorporates linear algebra and optimization principles. We propose a method that combines feature extraction techniques such as the Fourier transform with clustering algorithms to classify celestial objects based on their characteristics. The research examines the effectiveness of spectral clustering and K-means clustering in organizing astronomical images into meaningful groups, taking into account factors such as computer efficiency, clustering accuracy and interpretability. Experimenting with different datasets, including telescope images, we demonstrate the effectiveness of our approach in automating the classification of astronomical objects. Our results reveal insights into the underlying structure of astronomical knowledge and offer promising avenues for future research in computational astronomy. In general, this research advances both the field of astronomy and the application of mathematical methods to image analysis and clustering.

关键词： Image analysis Fourier transforms Accuracy Heuristic algorithms Clustering algorithms Linear algebra Feature extraction Optimization Astronomy Tuning

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Performance Evaluation and Effectiveness of Data-Driven Heart Disease Diagnosis

A Novel Approach for Performance Evaluation and Effectivenes...

引用

International Conference on Advances and Applications of Artificial Intelligence and Machine Learning, ICAAAIML 2023

作者： Islam, Md Aminul Nag, Anindya Das, Ayontika Faruque, Jobaer Shuvo, Shabbir Ahmed Nur, Abdullah Hafez Rahman, Md Habibur School of Engineering Computing and Mathematics Oxford Brookes University Oxford United Kingdom Department of Computer Science and Engineering Adamas University Kolkata India IRD Dhaka Bangladesh Offenburg University of Applied Sciences Offenburg Germany International Islamic University Chittagong Sonaichhari Bangladesh Department of Mathematics University of Chittagong Chittagong Bangladesh

ISBN: (纸本)9789819795062

Cardiovascular disease (CVD) has emerged as a prominent cause of mortality globally during the past few decades. To receive medical care for heart illness in a clinic or medical center, it is necessary to undergo costly diagnostic tests. Implementing machine learning (ML) algorithms presents a viable approach to monitoring the health of individuals with cardiac conditions, offering a potential solution to mitigate the financial burden of medical expenses. This study employed ten ML algorithms to predict heart disease, which distinguishes itself from others by incorporating three distinct cross-validation approaches and three sample techniques, enhancing our findings’ accuracy. Three different cross-validation strategies have been implemented in this study: holdout cross-validation, tenfold cross-validation, and stratified tenfold cross-validation. Each technique has been applied to every sample technique used in the study. DTC, RFC, KNN, and XGB algorithms exhibited the most favorable outcomes. Our recommended model is the RF Classifier implemented with near-miss under-sampling out of the four models considered. The model under consideration demonstrates the maximum level of accuracy, specifically 97.54%, 97.11%, and 99%, while employing the Extra Tree, Random Forest Classifier, and XGB. The ML model's performance was assessed using metrics like accuracy, error rate, precision, recall, F1-score, ROC AUC curve etc. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cardiology

来源：评论

学校读者我要写书评

暂无评论

Multichannel Steganography: A Provably Secure Hybrid Steganographic Model for Secure Communication

arXiv

引用

arXiv 2025年

作者： Omego, Obinna Bosy, Michal School of Computer Science and Mathematics Faculty of Engineering Computing and the Environment Kingston Universit London United Kingdom

This study introduces a novel steganographic model that synthesizes Steganography by Cover Modification (CMO) and Steganography by Cover Synthesis (CSY), enhancing both security and undetectability by generating cover messages or parameters while retaining the original cover’s form, thus minimizing detection risks and overcoming the limitations of single-method techniques. Building upon this model, a refined Steganographic Communication Protocol is proposed, enhancing resilience against sophisticated threats such as Multichannel Replay Attacks and Multichannel Man-in-the-Middle Attacks, fortifying the protocol against potential tampering and improving upon prior works. To evaluate the security of the proposed protocol, a novel adversarial model is developed simulating a probabilistic polynomial time (PPT) adversary capable of intercepting communications across multiple channels. This model assesses the adversary’s ability to compromise the protocol, providing a comprehensive security analysis. Finally, this study explores the practicality and adaptability of the model to both constrained environments like SMS banking and resource-rich settings such as blockchain transactions, demonstrating their potential to enhance financial services and security. These contributions present a robust and adaptable framework for secure steganographic communication, offering practical solutions for secure communications across diverse environments. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognition of Unit Segment and Polyline Graphs is ∃R-Complete 50th

Recognition of Unit Segment and Polyline Graphs is ∃R-Com...

引用

50th International Workshop on Graph-Theoretic Concepts in Computer science, WG 2024

作者： Hoffmann, Michael Miltzow, Tillmann Weber, Simon Wulf, Lasse Department of Computer Science ETH Zürich Zürich8001 Switzerland Department of Information and Computing Sciences Utrecht University Utrecht3584 CS Netherlands Institute of Discrete Mathematics Graz University of Technology Graz8010 Austria

ISBN: (纸本)9783031754081

Given a set of objects O in the plane, the corresponding intersection graph is defined as follows. A vertex is created for each object and an edge joins two vertices whenever the corresponding objects intersect. We study here the case of unit segments and polylines with exactly k bends. In the recognition problem, we are given a graph and want to decide whether the graph can be represented as the intersection graph of certain geometric objects. In previous work it was shown that various recognition problems are ∃R-complete, leaving unit segments and polylines as few remaining natural cases. We show that recognition for both families of objects is ∃R-complete. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and IoT-Enabled Accident Detection and Reporting for Smart Cities Domain

引用

KSII Transactions on Internet and Information Systems 2025年第4期19卷 1140-1166页

作者： Javed, Rawal Mazhar, Tehseen Aoun, Muhammad Shahzad, Tariq Al-AlShaikh, Halah A. Ghadi, Yazeed Yasin Saudagar, Abdul Khader Jilani Khan, Muhammad Amir School of Automation Central South University Changsha China School of Computer Science National College of Business Administration and Economics Lahore54000 Pakistan Department of Computer Science and Information Technology School Education Department Government of Punjab Layyah31200 Pakistan Department of CS IT Ghazi University Punjab Dera Ghazi Khan Pakistan School of Electrical Engineering Dept. of Electrical and Electronic Eng. Science University of Johannesburg Johannesburg2006 South Africa Riyadh11432 Saudi Arabia Department of Computer Science and Software Engineering Al Ain University Abu Dhabi12555 United Arab Emirates School of Computing Sciences College of Computing Informatics and Mathematics University Technology MARA Selangor Shah Alam40450 Malaysia

Even though numerous ICT-based solutions have been put forth for the detection of accidents and rescue missions, they often suffer from compatibility issues with different vehicles and are accompanied by high costs. This paper introduces a cutting-edge intelligent system designed for accident detection and rescue, mirroring human cognitive functions through integrating the Internet of Things (IoT) and artificial intelligence. A specialized kit for IoT has been created to identify accidents and gather comprehensive incident-related data, such as pressure, position, gravitational force, and speed. This information is then transmitted to the cloud for processing. A deep learning model is implemented in the cloud environment to verify the IoT module's output and activate the rescue mechanism when an accident is detected. The DL module, employing ensemble transfer learning with dynamic weights, aims to minimize false detection rates. Because there isn't an appropriate dataset available, a personalized dataset is generated from diverse online videos. To validate the proposed method, a comparative analysis is conducted on Yolo V4. Experimental results indicate that Yolo V4 outperforms, achieving training, validation, and test accuracies of 98.2% each. To assess the system's real-world applicability, it undergoes validation using a robot car model. Copyright © 2025 KSII.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Genghis Khan Shark based convolutional denoising autoencoder for quality enhancement of satellite images

引用

International Journal of Information Technology (Singapore) 2025年 1-14页

作者： Rajalakshmi, M. Subramanian, R. S. Sankara Tamilselvan, S. Bhuvanesh, A. Department of Computing Technologies School of Computing SRM Institute of Science and Technology Tamil Nadu Chennai India Department of Mathematics PSG Institute of Technology and Applied Research Tamil Nadu Coimbatore India Department of Electronics and Communication Engineering Sri Eshwar College of Engineering Tamil Nadu Coimbatore India Department of Electrical and Electronics Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli India

Satellite image processing often enhances feature perception and visibility for exact feature identification. Additionally, the change improves remote sensing data quality and clarity. Due to their long distances, these photos often have weather-related noise and distortion that must be fixed. This paper addresses these challenges with a Deep Learning (DL) satellite image denoising technique. An Adaptive Genghis Khan Shark Algorithm (AGKSA) and a Convolutional Denoised Autoencoder are used to improve satellite images in this study. The CDAE settings are optimized using the AGKSA while keeping important image attributes. AGKSA is used in this hybrid model to optimize CDAE performance under various noise conditions. Experimental results showed that the proposed model outperforms traditional image denoising approaches in satellite imagery feature extraction and visual quality. In very precise image processing applications like environmental monitoring and land use classification, the CDAE-AGKSA works well. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2025.

关键词： Adaptive Genghis Khan algorithm Convolutional denoised autoencoder Satellite image enhancement Satellite image processing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：